An Embedded Feature Selection Framework for Control
- URL: http://arxiv.org/abs/2206.11064v1
- Date: Sun, 19 Jun 2022 07:03:40 GMT
- Title: An Embedded Feature Selection Framework for Control
- Authors: Jiawen Wei, Fangyuan Wang, Wanxin Zeng, Wenwei Lin and Ning Gui
- Abstract summary: The Dual-world embedded Attentive Feature Selection (D-AFS) can efficiently select the most relevant sensors for the system under dynamic control.
By analyzing the DRL's response in two worlds, D-AFS can quantitatively identify respective features' importance towards control.
Results show that D-AFS successfully finds an optimized five-probes layout with 18.7% drag reduction.
- Score: 2.126171264016785
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Reducing sensor requirements while keeping optimal control performance is
crucial to many industrial control applications to achieve robust, low-cost,
and computation-efficient controllers. However, existing feature selection
solutions for the typical machine learning domain can hardly be applied in the
domain of control with changing dynamics. In this paper, a novel framework,
namely the Dual-world embedded Attentive Feature Selection (D-AFS), can
efficiently select the most relevant sensors for the system under dynamic
control. Rather than the one world used in most Deep Reinforcement Learning
(DRL) algorithms, D-AFS has both the real world and its virtual peer with
twisted features. By analyzing the DRL's response in two worlds, D-AFS can
quantitatively identify respective features' importance towards control. A
well-known active flow control problem, cylinder drag reduction, is used for
evaluation. Results show that D-AFS successfully finds an optimized five-probes
layout with 18.7\% drag reduction than the state-of-the-art solution with 151
probes and 49.2\% reduction than five-probes layout by human experts. We also
apply this solution to four OpenAI classical control cases. In all cases, D-AFS
achieves the same or better sensor configurations than originally provided
solutions. Results highlight, we argued, a new way to achieve efficient and
optimal sensor designs for experimental or industrial systems. Our source codes
are made publicly available at https://github.com/G-AILab/DAFSFluid.
Related papers
- Communication-Control Codesign for Large-Scale Wireless Networked Control Systems [80.30532872347668]
Wireless Networked Control Systems (WNCSs) are essential to Industry 4.0, enabling flexible control in applications, such as drone swarms and autonomous robots.
We propose a practical WNCS model that captures correlated dynamics among multiple control loops with spatially distributed sensors and actuators sharing limited wireless resources over multi-state Markov block-fading channels.
We develop a Deep Reinforcement Learning (DRL) algorithm that efficiently handles the hybrid action space, captures communication-control correlations, and ensures robust training despite sparse cross-domain variables and floating control inputs.
arXiv Detail & Related papers (2024-10-15T06:28:21Z) - Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution [51.83951489847344]
In robotics applications, smooth control signals are commonly preferred to reduce system wear and energy efficiency.
In this work, we aim to bridge this performance gap by growing discrete action spaces from coarse to fine control resolution.
Our work indicates that an adaptive control resolution in combination with value decomposition yields simple critic-only algorithms that yield surprisingly strong performance on continuous control tasks.
arXiv Detail & Related papers (2024-04-05T17:58:37Z) - Variational Autoencoders for exteroceptive perception in reinforcement learning-based collision avoidance [0.0]
Deep Reinforcement Learning (DRL) has emerged as a promising control framework.
Current DRL algorithms require disproportionally large computational resources to find near-optimal policies.
This paper presents a comprehensive exploration of our proposed approach in maritime control systems.
arXiv Detail & Related papers (2024-03-31T09:25:28Z) - HW-SW Optimization of DNNs for Privacy-preserving People Counting on
Low-resolution Infrared Arrays [9.806742394395322]
Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows.
Deep Neural Networks (DNNs) have been shown to be well-suited to process these sensor data in an accurate and efficient manner.
We propose a highly automated full-stack optimization flow for DNNs that goes from neural architecture search, mixed-precision quantization, and post-processing.
arXiv Detail & Related papers (2024-02-02T08:45:38Z) - UnLoc: A Universal Localization Method for Autonomous Vehicles using
LiDAR, Radar and/or Camera Input [51.150605800173366]
UnLoc is a novel unified neural modeling approach for localization with multi-sensor input in all weather conditions.
Our method is extensively evaluated on Oxford Radar RobotCar, ApolloSouthBay and Perth-WA datasets.
arXiv Detail & Related papers (2023-07-03T04:10:55Z) - Automating DBSCAN via Deep Reinforcement Learning [73.82740568765279]
We propose a novel Deep Reinforcement Learning guided automatic DBSCAN parameters search framework, namely DRL-DBSCAN.
The framework models the process of adjusting the parameter search direction by perceiving the clustering environment as a Markov decision process.
The framework consistently improves DBSCAN clustering accuracy by up to 26% and 25% respectively.
arXiv Detail & Related papers (2022-08-09T04:40:11Z) - Deep Reinforcement Learning with Shallow Controllers: An Experimental
Application to PID Tuning [3.9146761527401424]
We demonstrate the challenges in implementing a state of the art deep RL algorithm on a real physical system.
At the core of our approach is the use of a PID controller as the trainable RL policy.
arXiv Detail & Related papers (2021-11-13T18:48:28Z) - Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous
Vehicles and Multi-Agent RL [63.52264764099532]
We study the ability of autonomous vehicles to improve the throughput of a bottleneck using a fully decentralized control scheme in a mixed autonomy setting.
We apply multi-agent reinforcement algorithms to this problem and demonstrate that significant improvements in bottleneck throughput, from 20% at a 5% penetration rate to 33% at a 40% penetration rate, can be achieved.
arXiv Detail & Related papers (2020-10-30T22:06:05Z) - ASFD: Automatic and Scalable Face Detector [129.82350993748258]
We propose a novel Automatic and Scalable Face Detector (ASFD)
ASFD is based on a combination of neural architecture search techniques as well as a new loss design.
Our ASFD-D6 outperforms the prior strong competitors, and our lightweight ASFD-D0 runs at more than 120 FPS with Mobilenet for VGA-resolution images.
arXiv Detail & Related papers (2020-03-25T06:00:47Z) - Bayesian Optimization for Policy Search in High-Dimensional Systems via
Automatic Domain Selection [1.1240669509034296]
We propose to leverage results from optimal control to scale BO to higher dimensional control tasks.
We show how we can make use of a learned dynamics model in combination with a model-based controller to simplify the BO problem.
We present an experimental evaluation on real hardware, as well as simulated tasks including a 48-dimensional policy for a quadcopter.
arXiv Detail & Related papers (2020-01-21T09:04:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.